A Two-Stage LLM Framework for Accessible and Verified XAI Explanations

• URL: http://arxiv.org/abs/2604.12543v1
• Date: Tue, 14 Apr 2026 10:15:57 GMT
• Title: A Two-Stage LLM Framework for Accessible and Verified XAI Explanations
• Abstract summary: Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations.<n>This paper proposes a Two-Stage LLM Meta-Verification Framework that consists of (i) an Explainer LLM that converts raw XAI outputs into natural-language narratives, (ii) a Verifier LLM that assesses them in terms of faithfulness, coherence, completeness, and risk, and (iii) an iterative refeed mechanism that uses the Verifier's feedback to refine and improve them.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations. However, existing approaches often lack guarantees of accuracy, faithfulness, and completeness. At the same time, current efforts to evaluate such narratives remain largely subjective or confined to post-hoc scoring, offering no safeguards to prevent flawed explanations from reaching end-users. To address these limitations, this paper proposes a Two-Stage LLM Meta-Verification Framework that consists of (i) an Explainer LLM that converts raw XAI outputs into natural-language narratives, (ii) a Verifier LLM that assesses them in terms of faithfulness, coherence, completeness, and hallucination risk, and (iii) an iterative refeed mechanism that uses the Verifier's feedback to refine and improve them. Experiments across five XAI techniques and datasets, using three families of open-weight LLMs, show that verification is crucial for filtering unreliable explanations while improving linguistic accessibility compared with raw XAI outputs. In addition, the analysis of the Entropy Production Rate (EPR) during the refinement process indicates that the Verifier's feedback progressively guides the Explainer toward more stable and coherent reasoning. Overall, the proposed framework provides an efficient pathway toward more trustworthy and democratized XAI systems.

Related papers

• A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation [59.98516959731531]
  Abstract reasoning ability reflects intelligence and capacity of LLMs to extract and apply abstract rules.<n>Existing benchmarks either rely on expensive manual annotation, limiting their scale, or risk measuring memorization rather than genuine reasoning.<n>We introduce an automated pipeline named A2RBench, encompassing generation, expansion, evaluation, and analysis.
  arXiv  Detail & Related papers  (2026-05-17T06:14:20Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation [7.268064183717186]
  This study proposes an agentic XAI framework combining SHAP-based explainability with multimodal LLM-driven iterative refinement.<n>We tested this framework as an agricultural recommendation system using rice yield data from 26 fields in Japan.
  arXiv  Detail & Related papers  (2025-12-24T09:19:15Z)
• RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models [9.065322387043546]
  We introduce RHINO, a framework that decomposes Large Language Models into three interpretable phases mirroring human reasoning.<n> RHINO bridges the semantic gap between low-level observations and adversarial intent while improving output reliability through structured reasoning.<n>Our results demonstrate that RHINO significantly enhances the interpretability and scalability of threat analysis, offering a blueprint for deploying LLMs in operational security settings.
  arXiv  Detail & Related papers  (2025-10-16T02:25:46Z)
• Towards Transparent AI: A Survey on Explainable Language Models [22.70051215800476]
  Language Models (LMs) have significantly advanced natural language processing and enabled remarkable progress across diverse domains.<n>Lack of transparency is particularly problematic for adoption in high-stakes domains.<n>XAI methods have been well studied for non-LMs, but they face many limitations when applied to LMs.
  arXiv  Detail & Related papers  (2025-09-25T21:47:39Z)
• eX-NIDS: A Framework for Explainable Network Intrusion Detection Leveraging Large Language Models [3.8436076642278745]
  This paper introduces eX-NIDS, a framework designed to enhance interpretability in flow-based Network Intrusion Detection Systems (NIDS)<n>In our proposed framework, flows labelled as malicious by NIDS are initially processed through a module called the Prompt Augmenter.<n>This module extracts contextual information and Cyber Threat Intelligence (CTI)-related knowledge from these flows.<n>This enriched, context-specific data is then integrated with an input prompt for an LLM, enabling it to generate detailed explanations and interpretations of why the flow was identified as malicious by NIDS.
  arXiv  Detail & Related papers  (2025-07-22T05:26:21Z)
• Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond [55.984684518346924]
  We recast Knowledge Tracing as an inverse problem: learning the minimum natural-language summary that makes past answers explainable and future answers predictable.<n>Our Language Bottleneck Model (LBM) consists of an encoder LLM that writes an interpretable knowledge summary and a frozen decoder LLM that must reconstruct and predict student responses using only that summary text.<n> Experiments on synthetic arithmetic benchmarks and the large-scale Eedi dataset show that LBMs rival the accuracy of state-of-the-art KT and direct LLM methods while requiring orders-of-magnitude fewer student trajectories.
  arXiv  Detail & Related papers  (2025-06-20T13:21:14Z)
• Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations [1.6855625805565164]
  Large Language Models (LLMs) are used to translate outputs from explainability techniques, like feature-attribution weights, into a natural language explanation.<n>Recent findings suggest translating into human-like explanations does not necessarily enhance user understanding and may instead lead to overreliance on AI systems.
  arXiv  Detail & Related papers  (2025-04-16T18:45:18Z)
• Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era [76.12435556140515]
  XAI is being extended toward explaining Large Language Models (LLMs)<n>This paper analyzes how XAI can explain and improve LLM-based AI systems.<n>We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges.
  arXiv  Detail & Related papers  (2024-03-13T20:25:27Z)
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition [70.77292069313154]
  Large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF)
  arXiv  Detail & Related papers  (2024-02-08T07:21:45Z)
• FaithLM: Towards Faithful Explanations for Large Language Models [60.45183469474916]
  We introduce FaithLM, a model-agnostic framework that evaluates and improves the faithfulness of large language models.<n>We show that FaithLM consistently increases faithfulness and produces explanations more aligned with human rationales than strong self-explanation baselines.
  arXiv  Detail & Related papers  (2024-02-07T09:09:14Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.